基于门控循环单元的车辆跟驰行为仿真模型

doi:10.16182/j.issn1004731x.joss.20-FZ0438

系统仿真学报 ›› 2020, Vol. 32 ›› Issue (10): 1862-1873.doi: 10.16182/j.issn1004731x.joss.20-FZ0438

基于门控循环单元的车辆跟驰行为仿真模型

费蓉¹, 刘方², 谢国³, 黑新宏¹, 李莎莎¹, 胡博⁴

1.西安理工大学计算机学院,陕西西安 710048;
2.西北工业大学自动化学院,陕西西安 710129;
3.西安理工大学自动化学院,陕西西安 710048;
4.北京华电优控科技有限公司,北京 100193

收稿日期:2020-05-30 修回日期:2020-07-03 出版日期:2020-10-18 发布日期:2020-10-14
作者简介:费蓉(1980-),女,陕西西安,博士,副教授,研究方向为随机系统仿真,无人驾驶等。
基金资助:
国家重点研发计划(2018YFB1201500),国家自然科学基金(61773313,61873201,U1934222),陕西省重点研发计划(2019TD-014)

GRU-Based Car-Following Behavior Simulation Model

Fei Rong¹, Liu Fang², Xie Guo³, Hei Xinhong¹, Li Shasha¹, Hu Bo⁴

1. School of Computer Science, Xi'an University of Technology, Xi'an 710048, China;
2. School of Computer Science, Northwestern Polytechnical University, Xi'an 710129, China;
3. College of Automation Information and Engineering, Xi'an University of Technology, Xi'an 710048, China;
4. Beijing Huadian Youkong Technology Co. , Ltd. , Beijing 100193, China

Received:2020-05-30 Revised:2020-07-03 Online:2020-10-18 Published:2020-10-14

摘要/Abstract

摘要： 驾驶员记忆效应能有效提高车辆跟驰行为中的加速度预测准确率,结合General Motors (GM)跟驰模型与门控循环单元网络建立新的车辆跟驰模型。通过数据预处理获得有相似驾驶行为的小型车间车辆跟驰数据,校准新模型,从而确定模型的最优参数与结构,依据车辆跟驰特性通过仿真验证了模型有效性,与神经网络、支持向量回归进行对比,仿真结果证明,结合了L-BFGS优化的GRU车辆跟驰模型比仅考虑前导车与跟驰车间瞬时相互作用的车辆跟驰模型,能得到更高的仿真精度和稳定性。

关键词: 车辆跟驰, GM, GRU, SVR, 真实道路数据

Abstract: The accuracy of acceleration prediction can be effectively improved by the driver's memory in car-following behavior. A new car-following model based on the General Motors (GM) and the gate control unit (GRU) is proposed. The car-following data between small vehicles with similar driving behavior are obtained by data preprocessing. The established model is calibrated by the car-following data, and the optimal parameters and structure of the model are determined. According to car-following characteristics, the effectiveness of model is verified by simulation. It is confirmed that the model has high robustness and improved simulation accuracy comparing with the traditional models.

Key words: car-following, GM, GRU, SVR, actual road data

中图分类号:

U491

费蓉, 刘方, 谢国, 黑新宏, 李莎莎, 胡博. 基于门控循环单元的车辆跟驰行为仿真模型[J]. 系统仿真学报, 2020, 32(10): 1862-1873.

Fei Rong, Liu Fang, Xie Guo, Hei Xinhong, Li Shasha, Hu Bo. GRU-Based Car-Following Behavior Simulation Model[J]. Journal of System Simulation, 2020, 32(10): 1862-1873.

参考文献 26

[1]	王殿海, 金盛. 车辆跟驰行为建模的回顾与展望[J]. 中国公路学报, 2012, 25(1): 115-127.
	Wang Dianhai, Jin Sheng.Review and outlook of modelling of car following behavior[J]. China Journal of Highway and Transport, 2012, 25(1): 115-127.
[2]	Ciuffo B, Punzo V, Montanino M, et al.Thirty Years of Gipps' Car-Following Model: Applications, Developments, and New Features[J]. Transportation Research Record (S0361-1981), 2012, 2315: 89-99.
[3]	金盛. 考虑视觉注意特性的车辆跟驰行为建模[D]. 长春: 吉林大学, 2010.
	Jin Sheng.Modeling of car following behavior considering visual attention performance[D]. Changchun: Jilin University, 2010.
[4]	鲁斌. 基于数据驱动方法的车辆跟驰行为建模与分析[D]. 成都: 西南交通大学, 2017.
	Lu Bin.Modeling and analysis of car-following behavior using data-driven methods[D]. Chengdu: Southwest Jiaotong University, 2017.
[5]	Gazis D C, Herman R, Rothery R W, et al.Nonlinear Follow-the-Leader Models of Traffic Flow[J]. Operations Research (S0030-364X), 1961, 9(4): 545-567.
[6]	Rumelhart D E, Hinton G E, Williams R J, et al.Learning representations by back-propagating errors[J]. Nature (S0028-0836), 1988, 323(6088): 696-699.
[7]	Kehtarnavaz N, Groswold N, Miller K, et al.A Transportable Neural-Network Approach to Autonomous Vehicle Following[J]. IEEE Transactions on Vehicular Technology (S0018-9545), 1998, 47(2): 694-702.
[8]	贾洪飞, 隽志才, 王晓原. 基于神经网络的车辆跟驰模型的建立[J]. 公路交通科技, 2001(4): 92-94.
	Jia Hongfei, Juan Zhicai, Wang Xiaoyuan.Development of a car-following model based on artificial neural networks[J]. Journal of Highway and Transportation Research and Development, 2001(4): 92-94.
[9]	Kikuchi S, Chakroborty P.Car-following model based on fuzzy inference system[J]. Transportation Research Record (S0361-1981), 1992: 82-82.
[10]	Ma X.A Neural-Fuzzy Framework for Modeling Car-following Behavior[C]// 2006 IEEE International Conference on Systems, Man and Cybernetics. Taipei, Taiwan: IEEE, 2006: 1178-1183.
[11]	Cortes C, Vapnik V.Support-Vector Networks[J]. Machine Learning (S0885-6125), 1995, 20(3): 273-297.
[12]	Wei D, Liu H.Analysis of asymmetric driving behavior using a self-learning approach[J]. Transportation Research Part B-methodological (S0191-2615), 2013: 1-14.
[13]	王洪鹏, 陈锋. 基于在线支持向量回归的车辆跟驰模型研究[J]. 电子技术, 2018, 47(11): 21-28.
	Wang Hongpeng, Chen Feng.A car-following model based on online support vector regression[J]. Electronics R & D, 2018, 47(11): 21-28.
[14]	Elman J L.Finding Structure in Time[J]. Cognitive Science (S1551-6709), 1990, 14(2): 179-211.
[15]	Werbos P J.Backpropagation through time: what it does and how to do it[J]. Proceedings of the IEEE (S0018-9219), 1990, 78(10): 1550-1560.
[16]	Hochreiter S, Schmidhuber J.Long short-term memory[J]. Neural Computation (S0899-7667), 1997, 9(8): 1735-1780.
[17]	Cho K, Van Merrienboer B, Gulcehre C, et al.Learning Phrase Representations using RNN Encoder--Decoder for Statistical Machine Translation[C]// Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). Doha, Qatar: Association for Computational Linguistics, 2014, 1724-1734.
[18]	Wang X, Jiang R, Li L, et al.Capturing Car-Following Behaviors by Deep Learning[J]. IEEE Transactions on Intelligent Transportation Systems (S1524-9050), 2018, 19(3): 910-920.
[19]	FHWA. Next Generation Simulation[DB/OL].[2020-01-01]. https://ops.fhwa.dot.gov/trafficanalysis tools/ngsim.htm.
[20]	章三乐, 肖秋生, 任福田. 车辆跟驰理论的实用研究[J]. 北京工业大学学报, 1992(3): 20-27.
	Zhang Sanyue, Xiao Qiusheng, Ren Futian.Applied study of car-following theory[J]. Journal of Beijing Polyechnic University, 1992(3): 20-27.
[21]	杨林, 邢翠芳, 赵海冰. 汽车跟驰状态下驾驶员反应时间研究[J]. 计算技术与自动化, 2015, 34(3): 33-37.
	Yang Lin, Xing Cuifang, Zhao Haibing.Study on Driver's reaction Time (DRT) during car following[J]. Computing Technology and Automation, 2015, 34(3): 33-37.
[22]	Summala H.Brake Reaction Times and Driver Behavior Analysis[J]. Transportation Human Factors (S1093-9741), 2000, 2(3): 217-226.
[23]	乔晋. 车辆跟驰模型参数标定与验证研究[D]. 上海: 上海交通大学, 2008.
	Qiao Jin.Reaserching on parameters callbration and verification of car-following models[D]. Shanghai: Shanghai Jiaotong University, 2008.
[24]	Lu G, Cheng B, Wang Y, et al.A Car-Following Model Based on Quantified Homeostatic Risk Perception[J]. Mathematical Problems in Engineering (S1024-123X), 2013: 1-13.
[25]	Le Q V, Ngiam J, Coates A, et al.On optimization methods for deep learning[C]// ICML 2011. Bellevue, Washington, USA: Omnipress. 2011: 265-272.
[26]	Kurková V.Kolmogorov's theorem and multilayer neural networks[J]. Neural Networks (S0893-6080), 1992, 3(5): 501-506.

基于门控循环单元的车辆跟驰行为仿真模型

GRU-Based Car-Following Behavior Simulation Model

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献 26

相关文章 11

编辑推荐

Metrics

本文评价

[1]	戢晓峰, 戈艺澄. 基于深度学习的节假日高速公路交通流预测方法[J]. 系统仿真学报, 2020, 32(6): 1164-1171.
[2]	胡忠君, 刘艳秋, 李佳. 基于改进GM(1,1)的洪涝灾害应急物资动态需求预测[J]. 系统仿真学报, 2019, 31(4): 702-709.
[3]	贾宇涵, 吴建平, 杜怡曼, 刘明宇. 快速路车辆跟驰建模与仿真研究[J]. 系统仿真学报, 2019, 31(2): 248-256.
[4]	刘明宇, 吴建平, 王钰博, 何磊. 基于深度学习的交通流量预测[J]. 系统仿真学报, 2018, 30(11): 4100-4106.
[5]	吴定会, 杨德亮, 陈锦宝. 基于滑模观测器的永磁同步电机矢量控制[J]. 系统仿真学报, 2018, 30(11): 4256-4267.
[6]	徐杨杰, 王艳, 严大虎, 纪志成. 基于Newton插值与混合灰狼优化SVR的RFID定位算法[J]. 系统仿真学报, 2017, 29(9): 1921-1929.
[7]	王艳, 殷富成, 纪志成, 严大虎. 基于LWR-ABCSVR的WiFi指纹定位算法[J]. 系统仿真学报, 2017, 29(6): 1193-1200.
[8]	柯钢. 基于合作对策论的网络安全态势组合预测模型[J]. 系统仿真学报, 2017, 29(5): 1153-1159.
[9]	巫春玲, 巨永锋, 胡平, 段晨东. 用于再入弹道目标跟踪的Sigma点卡尔曼滤波器[J]. 系统仿真学报, 2016, 28(3): 640-647.
[10]	徐小平, 白博, 钱富才. 基于改进差分进化算法的Wiener模型辨识[J]. 系统仿真学报, 2016, 28(1): 147-153.
[11]	王子赟, 纪志成. 基于GM(2,1)和辨识算法的风电功率短期预测研究[J]. 系统仿真学报, 2015, 27(11): 2762-2769.